Skip to content

Muse Spark 1.2 (xhigh)

Available

Meta · 2026-08-05 · 32,000 tokens

An AI model from Meta, suited to a broad range of AI workloads.

Supported modalities:textcode

Quick Overview

Text Generation6/10
Code Generation7/10
Reasoning6/10
Multimodal5/10

Benchmark Results

Scores from leading benchmark suites.

artificial analysis intelligence56.8
artificial analysis coding72.2

Performance Metrics

Latency and throughput performance.

P50 Latency
0tokens/sec

Dive Deeper